Wenwen Qiang

Associate Professor@Institute of Software Chinese Academy of Sciences·中国·OpenReview

研究方向

LLM/MLLM · Causal Representation Learning · Self-Supervised Learning · Meta-Learning · Domain Adaptation/Generalization · Generative Model: VAE/GAN/Diffusion

5.2

On the Universality of Self-Supervised Learning

ICLR 2026Rejected

一作

4.5

CAIFormer: A Causal Informed Transformer for Multivariate Time Series Forecasting

ICLR 2026Rejected

二作

4.0

Teleporter Theory: A General and Simple Approach for Modeling Cross-World Counterfactual Causality

ICLR 2025Withdrawn

3.8

What Makes a Good Time-series Forecasting Model? A Causal Perspective

合作者 (20)

Wenwen Qiang

On the Universality of Self-Supervised Learning

CAIFormer: A Causal Informed Transformer for Multivariate Time Series Forecasting

Reward Model Generalization for Compute-Aware Test-Time Reasoning

Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMs

Towards the Causal Complete Cause of Multi-Modal Representation Learning

On the Out-of-Distribution Generalization of Self-Supervised Learning

On the Out-of-Distribution Generalization of Self-Supervised Learning

On the Universality of Self-Supervised Representation Learning

Learning Invariant Causal Mechanism from Vision-Language Models

Teleporter Theory: A General and Simple Approach for Modeling Cross-World Counterfactual Causality

What Makes a Good Time-series Forecasting Model? A Causal Perspective